In [1]:
# !pip install git+https://github.com/alberanid/rotopy
# !pip install pandas
# !pip install numpy
# !pip install matplotlib
# !pip install seaborn
# !pip install pandas_profiling --upgrade
# !pip install plotly
# !pip install wordcloud
# !pip install Flask
In [2]:
# Import Dataset
# Import File from Loacal Drive
# from google.colab import files
# data_to_load = files.upload()
# from google.colab import drive
# drive.mount('/content/drive')
In [3]:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
import collections
import plotly.express as px
import plotly.graph_objects as go
import nltk
import re
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
from nltk.probability import FreqDist
from nltk.util import ngrams
from plotly.subplots import make_subplots
from plotly.offline import iplot, init_notebook_mode
from wordcloud import WordCloud, STOPWORDS
from pandas_profiling import ProfileReport
%matplotlib inline
warnings.filterwarnings("ignore")
In [4]:
nltk.download('all')

[nltk_data] Downloading collection 'all'
[nltk_data]    | 
[nltk_data]    | Downloading package abc to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package abc is already up-to-date!
[nltk_data]    | Downloading package alpino to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package alpino is already up-to-date!
[nltk_data]    | Downloading package biocreative_ppi to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package biocreative_ppi is already up-to-date!
[nltk_data]    | Downloading package brown to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package brown is already up-to-date!
[nltk_data]    | Downloading package brown_tei to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package brown_tei is already up-to-date!
[nltk_data]    | Downloading package cess_cat to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package cess_cat is already up-to-date!
[nltk_data]    | Downloading package cess_esp to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package cess_esp is already up-to-date!
[nltk_data]    | Downloading package chat80 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package chat80 is already up-to-date!
[nltk_data]    | Downloading package city_database to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package city_database is already up-to-date!
[nltk_data]    | Downloading package cmudict to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package cmudict is already up-to-date!
[nltk_data]    | Downloading package comparative_sentences to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package comparative_sentences is already up-to-
[nltk_data]    |       date!
[nltk_data]    | Downloading package comtrans to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package comtrans is already up-to-date!
[nltk_data]    | Downloading package conll2000 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package conll2000 is already up-to-date!
[nltk_data]    | Downloading package conll2002 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package conll2002 is already up-to-date!
[nltk_data]    | Downloading package conll2007 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package conll2007 is already up-to-date!
[nltk_data]    | Downloading package crubadan to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package crubadan is already up-to-date!
[nltk_data]    | Downloading package dependency_treebank to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package dependency_treebank is already up-to-date!
[nltk_data]    | Downloading package dolch to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package dolch is already up-to-date!
[nltk_data]    | Downloading package europarl_raw to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package europarl_raw is already up-to-date!
[nltk_data]    | Downloading package floresta to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package floresta is already up-to-date!
[nltk_data]    | Downloading package framenet_v15 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package framenet_v15 is already up-to-date!
[nltk_data]    | Downloading package framenet_v17 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package framenet_v17 is already up-to-date!
[nltk_data]    | Downloading package gazetteers to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package gazetteers is already up-to-date!
[nltk_data]    | Downloading package genesis to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package genesis is already up-to-date!
[nltk_data]    | Downloading package gutenberg to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package gutenberg is already up-to-date!
[nltk_data]    | Downloading package ieer to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package ieer is already up-to-date!
[nltk_data]    | Downloading package inaugural to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package inaugural is already up-to-date!
[nltk_data]    | Downloading package indian to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package indian is already up-to-date!
[nltk_data]    | Downloading package jeita to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package jeita is already up-to-date!
[nltk_data]    | Downloading package kimmo to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package kimmo is already up-to-date!
[nltk_data]    | Downloading package knbc to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package knbc is already up-to-date!
[nltk_data]    | Downloading package lin_thesaurus to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package lin_thesaurus is already up-to-date!
[nltk_data]    | Downloading package mac_morpho to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package mac_morpho is already up-to-date!
[nltk_data]    | Downloading package machado to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package machado is already up-to-date!
[nltk_data]    | Downloading package masc_tagged to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package masc_tagged is already up-to-date!
[nltk_data]    | Downloading package moses_sample to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package moses_sample is already up-to-date!
[nltk_data]    | Downloading package movie_reviews to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package movie_reviews is already up-to-date!
[nltk_data]    | Downloading package names to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package names is already up-to-date!
[nltk_data]    | Downloading package nombank.1.0 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package nombank.1.0 is already up-to-date!
[nltk_data]    | Downloading package nps_chat to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package nps_chat is already up-to-date!
[nltk_data]    | Downloading package omw to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package omw is already up-to-date!
[nltk_data]    | Downloading package opinion_lexicon to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package opinion_lexicon is already up-to-date!
[nltk_data]    | Downloading package paradigms to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package paradigms is already up-to-date!
[nltk_data]    | Downloading package pil to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package pil is already up-to-date!
[nltk_data]    | Downloading package pl196x to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package pl196x is already up-to-date!
[nltk_data]    | Downloading package ppattach to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package ppattach is already up-to-date!
[nltk_data]    | Downloading package problem_reports to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package problem_reports is already up-to-date!
[nltk_data]    | Downloading package propbank to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package propbank is already up-to-date!
[nltk_data]    | Downloading package ptb to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package ptb is already up-to-date!
[nltk_data]    | Downloading package product_reviews_1 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package product_reviews_1 is already up-to-date!
[nltk_data]    | Downloading package product_reviews_2 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package product_reviews_2 is already up-to-date!
[nltk_data]    | Downloading package pros_cons to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package pros_cons is already up-to-date!
[nltk_data]    | Downloading package qc to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package qc is already up-to-date!
[nltk_data]    | Downloading package reuters to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package reuters is already up-to-date!
[nltk_data]    | Downloading package rte to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package rte is already up-to-date!
[nltk_data]    | Downloading package semcor to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package semcor is already up-to-date!
[nltk_data]    | Downloading package senseval to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package senseval is already up-to-date!
[nltk_data]    | Downloading package sentiwordnet to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package sentiwordnet is already up-to-date!
[nltk_data]    | Downloading package sentence_polarity to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package sentence_polarity is already up-to-date!
[nltk_data]    | Downloading package shakespeare to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package shakespeare is already up-to-date!
[nltk_data]    | Downloading package sinica_treebank to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package sinica_treebank is already up-to-date!
[nltk_data]    | Downloading package smultron to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package smultron is already up-to-date!
[nltk_data]    | Downloading package state_union to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package state_union is already up-to-date!
[nltk_data]    | Downloading package stopwords to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package stopwords is already up-to-date!
[nltk_data]    | Downloading package subjectivity to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package subjectivity is already up-to-date!
[nltk_data]    | Downloading package swadesh to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package swadesh is already up-to-date!
[nltk_data]    | Downloading package switchboard to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package switchboard is already up-to-date!
[nltk_data]    | Downloading package timit to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package timit is already up-to-date!
[nltk_data]    | Downloading package toolbox to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package toolbox is already up-to-date!
[nltk_data]    | Downloading package treebank to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package treebank is already up-to-date!
[nltk_data]    | Downloading package twitter_samples to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package twitter_samples is already up-to-date!
[nltk_data]    | Downloading package udhr to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package udhr is already up-to-date!
[nltk_data]    | Downloading package udhr2 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package udhr2 is already up-to-date!
[nltk_data]    | Downloading package unicode_samples to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package unicode_samples is already up-to-date!
[nltk_data]    | Downloading package universal_treebanks_v20 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package universal_treebanks_v20 is already up-to-
[nltk_data]    |       date!
[nltk_data]    | Downloading package verbnet to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package verbnet is already up-to-date!
[nltk_data]    | Downloading package verbnet3 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package verbnet3 is already up-to-date!
[nltk_data]    | Downloading package webtext to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package webtext is already up-to-date!
[nltk_data]    | Downloading package wordnet to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package wordnet is already up-to-date!
[nltk_data]    | Downloading package wordnet_ic to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package wordnet_ic is already up-to-date!
[nltk_data]    | Downloading package words to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package words is already up-to-date!
[nltk_data]    | Downloading package ycoe to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package ycoe is already up-to-date!
[nltk_data]    | Downloading package rslp to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package rslp is already up-to-date!
[nltk_data]    | Downloading package maxent_treebank_pos_tagger to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package maxent_treebank_pos_tagger is already up-
[nltk_data]    |       to-date!
[nltk_data]    | Downloading package universal_tagset to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package universal_tagset is already up-to-date!
[nltk_data]    | Downloading package maxent_ne_chunker to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package maxent_ne_chunker is already up-to-date!
[nltk_data]    | Downloading package punkt to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package punkt is already up-to-date!
[nltk_data]    | Downloading package book_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package book_grammars is already up-to-date!
[nltk_data]    | Downloading package sample_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package sample_grammars is already up-to-date!
[nltk_data]    | Downloading package spanish_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package spanish_grammars is already up-to-date!
[nltk_data]    | Downloading package basque_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package basque_grammars is already up-to-date!
[nltk_data]    | Downloading package large_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package large_grammars is already up-to-date!
[nltk_data]    | Downloading package tagsets to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package tagsets is already up-to-date!
[nltk_data]    | Downloading package snowball_data to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package snowball_data is already up-to-date!
[nltk_data]    | Downloading package bllip_wsj_no_aux to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package bllip_wsj_no_aux is already up-to-date!
[nltk_data]    | Downloading package word2vec_sample to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package word2vec_sample is already up-to-date!
[nltk_data]    | Downloading package panlex_swadesh to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package panlex_swadesh is already up-to-date!
[nltk_data]    | Downloading package mte_teip5 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package mte_teip5 is already up-to-date!
[nltk_data]    | Downloading package averaged_perceptron_tagger to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package averaged_perceptron_tagger is already up-
[nltk_data]    |       to-date!
[nltk_data]    | Downloading package averaged_perceptron_tagger_ru to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package averaged_perceptron_tagger_ru is already
[nltk_data]    |       up-to-date!
[nltk_data]    | Downloading package perluniprops to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package perluniprops is already up-to-date!
[nltk_data]    | Downloading package nonbreaking_prefixes to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package nonbreaking_prefixes is already up-to-date!
[nltk_data]    | Downloading package vader_lexicon to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package vader_lexicon is already up-to-date!
[nltk_data]    | Downloading package porter_test to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package porter_test is already up-to-date!
[nltk_data]    | Downloading package wmt15_eval to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package wmt15_eval is already up-to-date!
[nltk_data]    | Downloading package mwa_ppdb to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package mwa_ppdb is already up-to-date!
[nltk_data]    | 
[nltk_data]  Done downloading collection all
Out[4]:
True
In [5]:
# path = '/content/drive/MyDrive/Files/'

path = 'C:\\Users\\pawan\\OneDrive\\Desktop\\ott\\Data\\'
 
df_movies = pd.read_csv(path + 'ottmovies.csv')
 
df_movies.head()
Out[5]:
ID Title Year Age IMDb Rotten Tomatoes Directors Cast Genres Country Language Plotline Runtime Kind Seasons Netflix Hulu Prime Video Disney+ Type
0 1 Inception 2010 13+ 8.8 87% Christopher Nolan Leonardo DiCaprio,Joseph Gordon-Levitt,Elliot ... Action,Adventure,Sci-Fi,Thriller United States,United Kingdom English,Japanese,French Dom Cobb is a skilled thief, the absolute best... 148.0 movie NaN 1 0 0 0 0
1 2 The Matrix 1999 16+ 8.7 88% Lana Wachowski,Lilly Wachowski Keanu Reeves,Laurence Fishburne,Carrie-Anne Mo... Action,Sci-Fi United States English Thomas A. Anderson is a man living two lives. ... 136.0 movie NaN 1 0 0 0 0
2 3 Avengers: Infinity War 2018 13+ 8.4 85% Anthony Russo,Joe Russo Robert Downey Jr.,Chris Hemsworth,Mark Ruffalo... Action,Adventure,Sci-Fi United States English As the Avengers and their allies have continue... 149.0 movie NaN 1 0 0 0 0
3 4 Back to the Future 1985 7+ 8.5 96% Robert Zemeckis Michael J. Fox,Christopher Lloyd,Lea Thompson,... Adventure,Comedy,Sci-Fi United States English Marty McFly, a typical American teenager of th... 116.0 movie NaN 1 0 0 0 0
4 5 The Good, the Bad and the Ugly 1966 16+ 8.8 97% Sergio Leone Eli Wallach,Clint Eastwood,Lee Van Cleef,Aldo ... Western Italy,Spain,West Germany,United States Italian Blondie (The Good) (Clint Eastwood) is a profe... 161.0 movie NaN 1 0 1 0 0
In [6]:
# profile = ProfileReport(df_movies)
# profile
In [7]:
def data_investigate(df):
    print('No of Rows : ', df.shape[0])
    print('No of Coloums : ', df.shape[1])
    print('**'*25)
    print('Colums Names : \n', df.columns)
    print('**'*25)
    print('Datatype of Columns : \n', df.dtypes)
    print('**'*25)
    print('Missing Values : ')
    c = df.isnull().sum()
    c = c[c > 0]
    print(c)
    print('**'*25)
    print('Missing vaules %age wise :\n')
    print((100*(df.isnull().sum()/len(df.index))))
    print('**'*25)
    print('Pictorial Representation : ')
    plt.figure(figsize = (10, 10))
    sns.heatmap(df.isnull(), yticklabels = False, cbar = False)
    plt.show()
In [8]:
data_investigate(df_movies)

No of Rows :  16923
No of Coloums :  20
**************************************************
Colums Names : 
 Index(['ID', 'Title', 'Year', 'Age', 'IMDb', 'Rotten Tomatoes', 'Directors',
       'Cast', 'Genres', 'Country', 'Language', 'Plotline', 'Runtime', 'Kind',
       'Seasons', 'Netflix', 'Hulu', 'Prime Video', 'Disney+', 'Type'],
      dtype='object')
**************************************************
Datatype of Columns : 
 ID                   int64
Title               object
Year                 int64
Age                 object
IMDb               float64
Rotten Tomatoes     object
Directors           object
Cast                object
Genres              object
Country             object
Language            object
Plotline            object
Runtime            float64
Kind                object
Seasons            float64
Netflix              int64
Hulu                 int64
Prime Video          int64
Disney+              int64
Type                 int64
dtype: object
**************************************************
Missing Values : 
Age                 8457
IMDb                 328
Rotten Tomatoes    10437
Directors            357
Cast                 648
Genres               234
Country              303
Language             437
Plotline            4958
Runtime              382
Seasons            16923
dtype: int64
**************************************************
Missing vaules %age wise :

ID                   0.000000
Title                0.000000
Year                 0.000000
Age                 49.973409
IMDb                 1.938191
Rotten Tomatoes     61.673462
Directors            2.109555
Cast                 3.829108
Genres               1.382734
Country              1.790463
Language             2.582284
Plotline            29.297406
Runtime              2.257283
Kind                 0.000000
Seasons            100.000000
Netflix              0.000000
Hulu                 0.000000
Prime Video          0.000000
Disney+              0.000000
Type                 0.000000
dtype: float64
**************************************************
Pictorial Representation :
In [9]:
# ID
# df_movies = df_movies.drop(['ID'], axis = 1)
 
# Age
df_movies.loc[df_movies['Age'].isnull() & df_movies['Disney+'] == 1, "Age"] = '13'
# df_movies.fillna({'Age' : 18}, inplace = True)
df_movies.fillna({'Age' : 'NR'}, inplace = True)
df_movies['Age'].replace({'all': '0'}, inplace = True)
df_movies['Age'].replace({'7+': '7'}, inplace = True)
df_movies['Age'].replace({'13+': '13'}, inplace = True)
df_movies['Age'].replace({'16+': '16'}, inplace = True)
df_movies['Age'].replace({'18+': '18'}, inplace = True)
# df_movies['Age'] = df_movies['Age'].astype(int)
 
# IMDb
# df_movies.fillna({'IMDb' : df_movies['IMDb'].mean()}, inplace = True)
# df_movies.fillna({'IMDb' : df_movies['IMDb'].median()}, inplace = True)
df_movies.fillna({'IMDb' : "NA"}, inplace = True)
 
# Rotten Tomatoes
df_movies['Rotten Tomatoes'] = df_movies['Rotten Tomatoes'][df_movies['Rotten Tomatoes'].notnull()].str.replace('%', '').astype(int)
# df_movies['Rotten Tomatoes'] = df_movies['Rotten Tomatoes'][df_movies['Rotten Tomatoes'].notnull()].astype(int)
# df_movies.fillna({'Rotten Tomatoes' : df_movies['Rotten Tomatoes'].mean()}, inplace = True)
# df_movies.fillna({'Rotten Tomatoes' : df_movies['Rotten Tomatoes'].median()}, inplace = True)
# df_movies['Rotten Tomatoes'] = df_movies['Rotten Tomatoes'].astype(int)
df_movies.fillna({'Rotten Tomatoes' : "NA"}, inplace = True)
 
# Directors
# df_movies = df_movies.drop(['Directors'], axis = 1)
df_movies.fillna({'Directors' : "NA"}, inplace = True)
 
# Cast
df_movies.fillna({'Cast' : "NA"}, inplace = True)
 
# Genres
df_movies.fillna({'Genres': "NA"}, inplace = True)
 
# Country
df_movies.fillna({'Country': "NA"}, inplace = True)
 
# Language
df_movies.fillna({'Language': "NA"}, inplace = True)
 
# Plotline
df_movies.fillna({'Plotline': "NA"}, inplace = True)
 
# Runtime
# df_movies.fillna({'Runtime' : df_movies['Runtime'].mean()}, inplace = True)
# df_movies['Runtime'] = df_movies['Runtime'].astype(int)
df_movies.fillna({'Runtime' : "NA"}, inplace = True)
 
# Kind
# df_movies.fillna({'Kind': "NA"}, inplace = True)
 
# Type
# df_movies.fillna({'Type': "NA"}, inplace = True)
# df_movies = df_movies.drop(['Type'], axis = 1)
 
# Seasons
# df_movies.fillna({'Seasons': 1}, inplace = True)
# df_movies.fillna({'Seasons': "NA"}, inplace = True)
df_movies = df_movies.drop(['Seasons'], axis = 1)
# df_movies['Seasons'] = df_movies['Seasons'].astype(int)
# df_movies.fillna({'Seasons' : df_movies['Seasons'].mean()}, inplace = True)
# df_movies['Seasons'] = df_movies['Seasons'].astype(int)
 
# Service Provider
df_movies['Service Provider'] = df_movies.loc[:, ['Netflix', 'Prime Video', 'Disney+', 'Hulu']].idxmax(axis = 1)
# df_movies.drop(['Netflix','Prime Video','Disney+','Hulu'], axis = 1)

# Removing Duplicate and Missing Entries
df_movies.dropna(how = 'any', inplace = True)
df_movies.drop_duplicates(inplace = True)
In [10]:
data_investigate(df_movies)

No of Rows :  16923
No of Coloums :  20
**************************************************
Colums Names : 
 Index(['ID', 'Title', 'Year', 'Age', 'IMDb', 'Rotten Tomatoes', 'Directors',
       'Cast', 'Genres', 'Country', 'Language', 'Plotline', 'Runtime', 'Kind',
       'Netflix', 'Hulu', 'Prime Video', 'Disney+', 'Type',
       'Service Provider'],
      dtype='object')
**************************************************
Datatype of Columns : 
 ID                   int64
Title               object
Year                 int64
Age                 object
IMDb                object
Rotten Tomatoes     object
Directors           object
Cast                object
Genres              object
Country             object
Language            object
Plotline            object
Runtime             object
Kind                object
Netflix              int64
Hulu                 int64
Prime Video          int64
Disney+              int64
Type                 int64
Service Provider    object
dtype: object
**************************************************
Missing Values : 
Series([], dtype: int64)
**************************************************
Missing vaules %age wise :

ID                  0.0
Title               0.0
Year                0.0
Age                 0.0
IMDb                0.0
Rotten Tomatoes     0.0
Directors           0.0
Cast                0.0
Genres              0.0
Country             0.0
Language            0.0
Plotline            0.0
Runtime             0.0
Kind                0.0
Netflix             0.0
Hulu                0.0
Prime Video         0.0
Disney+             0.0
Type                0.0
Service Provider    0.0
dtype: float64
**************************************************
Pictorial Representation :
In [11]:
df_movies.head()
Out[11]:
ID Title Year Age IMDb Rotten Tomatoes Directors Cast Genres Country Language Plotline Runtime Kind Netflix Hulu Prime Video Disney+ Type Service Provider
0 1 Inception 2010 13 8.8 87 Christopher Nolan Leonardo DiCaprio,Joseph Gordon-Levitt,Elliot ... Action,Adventure,Sci-Fi,Thriller United States,United Kingdom English,Japanese,French Dom Cobb is a skilled thief, the absolute best... 148 movie 1 0 0 0 0 Netflix
1 2 The Matrix 1999 16 8.7 88 Lana Wachowski,Lilly Wachowski Keanu Reeves,Laurence Fishburne,Carrie-Anne Mo... Action,Sci-Fi United States English Thomas A. Anderson is a man living two lives. ... 136 movie 1 0 0 0 0 Netflix
2 3 Avengers: Infinity War 2018 13 8.4 85 Anthony Russo,Joe Russo Robert Downey Jr.,Chris Hemsworth,Mark Ruffalo... Action,Adventure,Sci-Fi United States English As the Avengers and their allies have continue... 149 movie 1 0 0 0 0 Netflix
3 4 Back to the Future 1985 7 8.5 96 Robert Zemeckis Michael J. Fox,Christopher Lloyd,Lea Thompson,... Adventure,Comedy,Sci-Fi United States English Marty McFly, a typical American teenager of th... 116 movie 1 0 0 0 0 Netflix
4 5 The Good, the Bad and the Ugly 1966 16 8.8 97 Sergio Leone Eli Wallach,Clint Eastwood,Lee Van Cleef,Aldo ... Western Italy,Spain,West Germany,United States Italian Blondie (The Good) (Clint Eastwood) is a profe... 161 movie 1 0 1 0 0 Netflix
In [12]:
df_movies.describe()
Out[12]:
ID Year Netflix Hulu Prime Video Disney+ Type
count 16923.000000 16923.000000 16923.000000 16923.000000 16923.000000 16923.000000 16923.0
mean 8462.000000 2003.211901 0.214915 0.062637 0.727235 0.033150 0.0
std 4885.393638 20.526532 0.410775 0.242315 0.445394 0.179034 0.0
min 1.000000 1901.000000 0.000000 0.000000 0.000000 0.000000 0.0
25% 4231.500000 2001.000000 0.000000 0.000000 0.000000 0.000000 0.0
50% 8462.000000 2012.000000 0.000000 0.000000 1.000000 0.000000 0.0
75% 12692.500000 2016.000000 0.000000 0.000000 1.000000 0.000000 0.0
max 16923.000000 2020.000000 1.000000 1.000000 1.000000 1.000000 0.0
In [13]:
df_movies.corr()
Out[13]:
ID Year Netflix Hulu Prime Video Disney+ Type
ID 1.000000 -0.217816 -0.644470 -0.129926 0.469301 0.263530 NaN
Year -0.217816 1.000000 0.256151 0.101337 -0.255578 -0.047258 NaN
Netflix -0.644470 0.256151 1.000000 -0.118032 -0.745141 -0.089649 NaN
Hulu -0.129926 0.101337 -0.118032 1.000000 -0.284654 -0.039693 NaN
Prime Video 0.469301 -0.255578 -0.745141 -0.284654 1.000000 -0.289008 NaN
Disney+ 0.263530 -0.047258 -0.089649 -0.039693 -0.289008 1.000000 NaN
Type NaN NaN NaN NaN NaN NaN NaN
In [14]:
# df_movies.sort_values('Year', ascending = True)
# df_movies.sort_values('Rotten Tomatoes', ascending = False)
In [15]:
# df_movies.to_csv(path_or_buf= '/content/drive/MyDrive/Files/updated_ottmovies.csv', index = False)
 
# path = '/content/drive/MyDrive/Files/'
 
# udf_movies = pd.read_csv(path + 'updated_ottmovies.csv')
 
# udf_movies
In [16]:
# df_netflix_movies = df_movies.loc[(df_movies['Netflix'] > 0)]
# df_hulu_movies = df_movies.loc[(df_movies['Hulu'] > 0)]
# df_prime_video_movies = df_movies.loc[(df_movies['Prime Video'] > 0)]
# df_disney_movies = df_movies.loc[(df_movies['Disney+'] > 0)]
In [17]:
df_netflix_only_movies = df_movies[(df_movies['Netflix'] == 1) & (df_movies['Hulu'] == 0) & (df_movies['Prime Video'] == 0 ) & (df_movies['Disney+'] == 0)]
df_hulu_only_movies = df_movies[(df_movies['Netflix'] == 0) & (df_movies['Hulu'] == 1) & (df_movies['Prime Video'] == 0 ) & (df_movies['Disney+'] == 0)]
df_prime_video_only_movies = df_movies[(df_movies['Netflix'] == 0) & (df_movies['Hulu'] == 0) & (df_movies['Prime Video'] == 1 ) & (df_movies['Disney+'] == 0)]
df_disney_only_movies = df_movies[(df_movies['Netflix'] == 0) & (df_movies['Hulu'] == 0) & (df_movies['Prime Video'] == 0 ) & (df_movies['Disney+'] == 1)]
In [18]:
df_movies_roto = df_movies.copy()
In [19]:
df_movies_roto.drop(df_movies_roto.loc[df_movies_roto['Rotten Tomatoes'] == "NA"].index, inplace = True)
# df_movies_roto = df_movies_roto[df_movies_roto.Rotten Tomatoes != "NA"]
df_movies_roto['Rotten Tomatoes'] = df_movies_roto['Rotten Tomatoes'].astype(int)
In [20]:
# Creating distinct dataframes only with the movies present on individual streaming platforms
netflix_roto_movies = df_movies_roto.loc[df_movies_roto['Netflix'] == 1]
hulu_roto_movies = df_movies_roto.loc[df_movies_roto['Hulu'] == 1]
prime_video_roto_movies = df_movies_roto.loc[df_movies_roto['Prime Video'] == 1]
disney_roto_movies = df_movies_roto.loc[df_movies_roto['Disney+'] == 1]
In [21]:
df_movies_roto_group = df_movies_roto.copy()
In [22]:
plt.figure(figsize = (10, 10))
corr = df_movies_roto.corr()
# Plot figsize
fig, ax = plt.subplots(figsize=(10, 8))
# Generate Heat Map, allow annotations and place floats in map
sns.heatmap(corr, cmap = 'magma', annot = True, fmt = ".2f")
# Apply xticks
plt.xticks(range(len(corr.columns)), corr.columns);
# Apply yticks
plt.yticks(range(len(corr.columns)), corr.columns)
# show plot
plt.show()
fig.show()

<Figure size 720x720 with 0 Axes>
In [23]:
df_roto_high_movies = df_movies_roto.sort_values(by = 'Rotten Tomatoes', ascending = False).reset_index()
df_roto_high_movies = df_roto_high_movies.drop(['index'], axis = 1)
# filter = (df_movies_roto['Rotten Tomatoes'] == (df_movies_roto['Rotten Tomatoes'].max()))
# df_roto_high_movies = df_movies_roto[filter]
 
# highest_rated_movies = df_movies_roto.loc[df_movies_roto['Rotten Tomatoes'].idxmax()]
 
print('\nMovies with Highest Ever Rotten Tomatoes  are : \n')
df_roto_high_movies.head(5)

Movies with Highest Ever Rotten Tomatoes  are :
Out[23]:
ID Title Year Age IMDb Rotten Tomatoes Directors Cast Genres Country Language Plotline Runtime Kind Netflix Hulu Prime Video Disney+ Type Service Provider
0 4561 Pyaasa 1957 NR 8.5 100 Guru Dutt Guru Dutt,Waheeda Rehman,Mala Sinha,Rehman,Joh... Drama,Musical,Romance India Hindi Unemployed Vijay is the youngest in his family... 146 movie 0 0 1 0 0 Prime Video
1 4405 My Name Is Nobody 1973 7 7.5 100 Tonino Valerii Terence Hill,Henry Fonda,Jean Martin,R.G. Arms... Comedy,Western Italy,France,West Germany Italian Jack Beauregard, once the greatest gunslinger ... 116 movie 0 0 1 0 0 Prime Video
2 5255 Racing Dreams 2010 7 7 100 Marshall Curry Annabeth Barnes,Josh Hobson,Brandon Warren,Rus... Documentary,Sport United States English Sidney Poitier returned to the big screen in t... 93 movie 0 0 1 0 0 Prime Video
3 5259 Shoot to Kill 1988 16 6.8 100 Roger Spottiswoode Sidney Poitier,Tom Berenger,Kirstie Alley,Clan... Action,Adventure,Crime,Drama,Thriller United States,Canada English Down on his luck and perpetually impecunious, ... 110 movie 0 0 1 0 0 Prime Video
4 412 Ice Guardians 2016 NR 7.5 100 Brett Harvey Jay Baruchel,Jarome Iginla,Chris Chelios,Brett... Documentary,Sport Canada,Ireland,United States English NA 108 movie 1 0 0 0 0 Netflix
In [24]:
fig = px.bar(y = df_roto_high_movies['Title'][:15],
             x = df_roto_high_movies['Rotten Tomatoes'][:15], 
             color = df_roto_high_movies['Rotten Tomatoes'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Rotten Tomatoes : Rating'},
             title  = 'Movies with Highest Rotten Tomatoes : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()
In [25]:
df_roto_low_movies = df_movies_roto.sort_values(by = 'Rotten Tomatoes', ascending = True).reset_index()
df_roto_low_movies = df_roto_low_movies.drop(['index'], axis = 1)
# filter = (df_movies_roto['Rotten Tomatoes'] == (df_movies_roto['Rotten Tomatoes'].min()))
# df_roto_low_movies = df_movies_roto[filter]

print('\nMovies with Lowest Ever Rotten Tomatoes  are : \n')
df_roto_low_movies.head(5)

Movies with Lowest Ever Rotten Tomatoes  are :
Out[25]:
ID Title Year Age IMDb Rotten Tomatoes Directors Cast Genres Country Language Plotline Runtime Kind Netflix Hulu Prime Video Disney+ Type Service Provider
0 2015 Term Life 2016 16 5.6 0 Peter Billingsley Vince Vaughn,Hailee Steinfeld,Bill Paxton,Jona... Action,Crime,Drama,Thriller United States English NA 93 movie 1 0 0 0 0 Netflix
1 8168 Speed Kills 2018 16 4.3 0 Jodi Scurfield John Travolta,Katheryn Winnick,Jennifer Esposi... Action,Crime,Drama,Thriller Puerto Rico,United States English,Spanish NA 102 movie 0 0 1 0 0 Prime Video
2 3331 John Henry 2020 16 3.5 0 Will Forbes Terry Crews,Jamila Velazquez,Ludacris,Ken Fore... Drama,Thriller United States English Ex-gang member John Henry (Terry Crews) is a q... 91 movie 1 0 0 0 0 Netflix
3 1422 The Coldest Game 2019 18 6.2 0 Lukasz Kosmicki Bill Pullman,Lotte Verbeek,James Bloor,Robert ... History,Sport,Thriller Poland,United States English,Russian Playing a major chess match in Warsaw against ... 102 movie 1 0 0 0 0 Netflix
4 9800 Shadows & Lies 2010 16 4.3 0 Jay Anania James Franco,Julianne Nicholson,Martin Donovan... Crime,Drama United States English NA 100 movie 0 0 1 0 0 Prime Video
In [26]:
fig = px.bar(y = df_roto_low_movies['Title'][:15],
             x = df_roto_low_movies['Rotten Tomatoes'][:15], 
             color = df_roto_low_movies['Rotten Tomatoes'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Rotten Tomatoes : Rating'},
             title  = 'Movies with Lowest Rotten Tomatoes : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()
In [27]:
print(f'''
      Total '{df_movies_roto['Rotten Tomatoes'].unique().shape[0]}' unique Rotten Tomatoes s were Given, They were Like this,\n
      
{df_movies_roto.sort_values(by = 'Rotten Tomatoes', ascending = False)['Rotten Tomatoes'].unique()}\n
 
      The Highest Ever Rotten Tomatoes Ever Any Movie Got is '{df_roto_high_movies['Title'][0]}' : '{df_roto_high_movies['Rotten Tomatoes'].max()}'\n
 
      The Lowest Ever Rotten Tomatoes Ever Any Movie Got is '{df_roto_low_movies['Title'][0]}' : '{df_roto_low_movies['Rotten Tomatoes'].min()}'\n
      ''')

      Total '101' unique Rotten Tomatoes s were Given, They were Like this,

      
[100  99  98  97  96  95  94  93  92  91  90  89  88  87  86  85  84  83
  82  81  80  79  78  77  76  75  74  73  72  71  70  69  68  67  66  65
  64  63  62  61  60  59  58  57  56  55  54  53  52  51  50  49  48  47
  46  45  44  43  42  41  40  39  38  37  36  35  34  33  32  31  30  29
  28  27  26  25  24  23  22  21  20  19  18  17  16  15  14  13  12  11
  10   9   8   7   6   5   4   3   2   1   0]

 
      The Highest Ever Rotten Tomatoes Ever Any Movie Got is 'Pyaasa' : '100'

 
      The Lowest Ever Rotten Tomatoes Ever Any Movie Got is 'Term Life' : '0'
In [28]:
netflix_roto_high_movies = df_roto_high_movies.loc[df_roto_high_movies['Netflix']==1].reset_index()
netflix_roto_high_movies = netflix_roto_high_movies.drop(['index'], axis = 1)
 
netflix_roto_low_movies = df_roto_low_movies.loc[df_roto_low_movies['Netflix']==1].reset_index()
netflix_roto_low_movies = netflix_roto_low_movies.drop(['index'], axis = 1)
 
netflix_roto_high_movies.head(5)
Out[28]:
ID Title Year Age IMDb Rotten Tomatoes Directors Cast Genres Country Language Plotline Runtime Kind Netflix Hulu Prime Video Disney+ Type Service Provider
0 412 Ice Guardians 2016 NR 7.5 100 Brett Harvey Jay Baruchel,Jarome Iginla,Chris Chelios,Brett... Documentary,Sport Canada,Ireland,United States English NA 108 movie 1 0 0 0 0 Netflix
1 2340 Maria Bamford: Old Baby 2017 18 6 100 Jessica Yu Maria Bamford,Rhea Butcher,Alex Blue Davis,Mel... Documentary,Comedy United States English NA 64 movie 1 0 0 0 0 Netflix
2 946 07:19 2016 NR 5.9 100 Jorge Michel Grau Carmen Beato,Demián Bichir,Héctor Bonilla,Octa... Drama,History Mexico Spanish Martin and Fernando are at the reception of th... 94 movie 1 0 0 0 0 Netflix
3 421 Shirkers 2018 NR 7.4 100 Sandi Tan Sandi Tan,Jasmine Kin Kia Ng,Philip Cheah,Soph... Documentary United States,United Kingdom English In 1992, teenager Sandi Tan and her friends So... 97 movie 1 0 0 0 0 Netflix
4 970 Restless Creature: Wendy Whelan 2017 NR 7.1 100 Linda Saffire,Adam Schlesinger Peter Martins,David Prottas,Wendy Whelan Documentary United States English NA 90 movie 1 0 0 0 0 Netflix
In [29]:
fig = px.bar(y = netflix_roto_high_movies['Title'][:15],
             x = netflix_roto_high_movies['Rotten Tomatoes'][:15], 
             color = netflix_roto_high_movies['Rotten Tomatoes'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Rotten Tomatoes : Rating'},
             title  = 'Movies with Highest Rotten Tomatoes : Netflix')

fig.update_layout(plot_bgcolor = 'white')
fig.show()
In [30]:
fig = px.bar(y = netflix_roto_low_movies['Title'][:15],
             x = netflix_roto_low_movies['Rotten Tomatoes'][:15], 
             color = netflix_roto_low_movies['Rotten Tomatoes'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Rotten Tomatoes : Rating'},
             title  = 'Movies with Lowest Rotten Tomatoes : Netflix')

fig.update_layout(plot_bgcolor = 'white')
fig.show()
In [31]:
hulu_roto_high_movies = df_roto_high_movies.loc[df_roto_high_movies['Hulu']==1].reset_index()
hulu_roto_high_movies = hulu_roto_high_movies.drop(['index'], axis = 1)
 
hulu_roto_low_movies = df_roto_low_movies.loc[df_roto_low_movies['Hulu']==1].reset_index()
hulu_roto_low_movies = hulu_roto_low_movies.drop(['index'], axis = 1)
 
hulu_roto_high_movies.head(5)
Out[31]:
ID Title Year Age IMDb Rotten Tomatoes Directors Cast Genres Country Language Plotline Runtime Kind Netflix Hulu Prime Video Disney+ Type Service Provider
0 3665 After the Screaming Stops 2018 18 7.2 100 Joe Pearlman,David Soutar Luke Goss,Matt Goss,Ron Perlman,Robin Antin,Ge... Documentary,Music United Kingdom English In the 1980s, "Bros" were one of the biggest b... 98 movie 0 1 0 0 0 Hulu
1 3638 Andy Irons: Kissed by God 2018 NR 8.2 100 Steve Jones,Todd Jones Bruce Irons,Lyndie Irons,Kelly Slater Documentary United States English A film about bipolar disorder and opioid addic... 100 movie 0 1 1 0 0 Prime Video
2 3656 Burn 2012 16 5.7 100 Mike Gan Tilda Cobham-Hervey,Josh Hutcherson,Suki Water... Comedy,Crime,Thriller United States English NA 88 movie 0 1 1 0 0 Prime Video
3 3739 Food Evolution 2017 7 7 100 Scott Hamilton Kennedy Raoul Adamchak,Charles Benbrook,Karl Haro von ... Documentary United States English Food Evolution looks at one of the most critic... 92 movie 0 1 0 0 0 Hulu
4 3741 The Den 2013 16 6 100 Zachary Donohue Melanie Papalia,David Schlachtenhaufen,Adam Sh... Horror,Mystery,Thriller United States English A young woman studying the habits of webcam ch... 76 movie 0 1 0 0 0 Hulu
In [32]:
fig = px.bar(y = hulu_roto_high_movies['Title'][:15],
             x = hulu_roto_high_movies['Rotten Tomatoes'][:15], 
             color = hulu_roto_high_movies['Rotten Tomatoes'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Rotten Tomatoes : Rating'},
             title  = 'Movies with Highest Rotten Tomatoes : Hulu')

fig.update_layout(plot_bgcolor = 'white')
fig.show()
In [33]:
fig = px.bar(y = hulu_roto_low_movies['Title'][:15],
             x = hulu_roto_low_movies['Rotten Tomatoes'][:15], 
             color = hulu_roto_low_movies['Rotten Tomatoes'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Rotten Tomatoes : Rating'},
             title  = 'Movies with Lowest Rotten Tomatoes : Hulu')

fig.update_layout(plot_bgcolor = 'white')
fig.show()
In [34]:
prime_video_roto_high_movies = df_roto_high_movies.loc[df_roto_high_movies['Prime Video']==1].reset_index()
prime_video_roto_high_movies = prime_video_roto_high_movies.drop(['index'], axis = 1)
 
prime_video_roto_low_movies = df_roto_low_movies.loc[df_roto_low_movies['Prime Video']==1].reset_index()
prime_video_roto_low_movies = prime_video_roto_low_movies.drop(['index'], axis = 1)
 
prime_video_roto_high_movies.head(5)
Out[34]:
ID Title Year Age IMDb Rotten Tomatoes Directors Cast Genres Country Language Plotline Runtime Kind Netflix Hulu Prime Video Disney+ Type Service Provider
0 4561 Pyaasa 1957 NR 8.5 100 Guru Dutt Guru Dutt,Waheeda Rehman,Mala Sinha,Rehman,Joh... Drama,Musical,Romance India Hindi Unemployed Vijay is the youngest in his family... 146 movie 0 0 1 0 0 Prime Video
1 4405 My Name Is Nobody 1973 7 7.5 100 Tonino Valerii Terence Hill,Henry Fonda,Jean Martin,R.G. Arms... Comedy,Western Italy,France,West Germany Italian Jack Beauregard, once the greatest gunslinger ... 116 movie 0 0 1 0 0 Prime Video
2 5255 Racing Dreams 2010 7 7 100 Marshall Curry Annabeth Barnes,Josh Hobson,Brandon Warren,Rus... Documentary,Sport United States English Sidney Poitier returned to the big screen in t... 93 movie 0 0 1 0 0 Prime Video
3 5259 Shoot to Kill 1988 16 6.8 100 Roger Spottiswoode Sidney Poitier,Tom Berenger,Kirstie Alley,Clan... Action,Adventure,Crime,Drama,Thriller United States,Canada English Down on his luck and perpetually impecunious, ... 110 movie 0 0 1 0 0 Prime Video
4 10259 The Surface 2015 NR 4.8 100 Gil Cates Jr. Sean Astin,Mimi Rogers,Chris Mulkey,John Emmet... Drama,Thriller United States English NA 90 movie 0 0 1 0 0 Prime Video
In [35]:
fig = px.bar(y = prime_video_roto_high_movies['Title'][:15],
             x = prime_video_roto_high_movies['Rotten Tomatoes'][:15], 
             color = prime_video_roto_high_movies['Rotten Tomatoes'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Rotten Tomatoes : Rating'},
             title  = 'Movies with Highest Rotten Tomatoes : Prime Video')

fig.update_layout(plot_bgcolor = 'white')
fig.show()
In [36]:
fig = px.bar(y = prime_video_roto_low_movies['Title'][:15],
             x = prime_video_roto_low_movies['Rotten Tomatoes'][:15], 
             color = prime_video_roto_low_movies['Rotten Tomatoes'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Rotten Tomatoes : Rating'},
             title  = 'Movies with Lowest Rotten Tomatoes : Prime Video')

fig.update_layout(plot_bgcolor = 'white')
fig.show()
In [37]:
disney_roto_high_movies = df_roto_high_movies.loc[df_roto_high_movies['Disney+']==1].reset_index()
disney_roto_high_movies = disney_roto_high_movies.drop(['index'], axis = 1)
 
disney_roto_low_movies = df_roto_low_movies.loc[df_roto_low_movies['Disney+']==1].reset_index()
disney_roto_low_movies = disney_roto_low_movies.drop(['index'], axis = 1)
 
disney_roto_high_movies.head(5)
Out[37]:
ID Title Year Age IMDb Rotten Tomatoes Directors Cast Genres Country Language Plotline Runtime Kind Netflix Hulu Prime Video Disney+ Type Service Provider
0 15804 The Many Adventures of Winnie the Pooh 1977 0 7.6 100 John Lounsbery,Wolfgang Reitherman,Ben Sharpsteen Sebastian Cabot,Junius Matthews,Barbara Luddy,... Animation,Adventure,Comedy,Family,Musical United States English When young Victor's pet dog Sparky (who stars ... 74 movie 0 0 0 1 0 Disney+
1 15807 Mickey's Christmas Carol 1983 0 8 100 Burny Mattinson Alan Young,Wayne Allwine,Hal Smith,Will Ryan,E... Animation,Short,Comedy,Family,Fantasy United States English Sam Flynn, the tech-savvy 27-year-old son of K... 26 movie 0 0 0 1 0 Disney+
2 15844 Old Yeller 1957 0 7.3 100 Robert Stevenson Dorothy McGuire,Fess Parker,Jeff York,Chuck Co... Adventure,Drama,Family,Western United States English Two stories. The Wind in the Willows: Concise ... 83 movie 0 0 0 1 0 Disney+
3 15846 Phineas and Ferb the Movie: Across the 2nd Dim... 2011 0 7.4 100 Robert Hughes,Dan Povenmire,Jay Lender,Jeff 'S... Vincent Martella,Ashley Tisdale,Thomas Brodie-... Animation,Action,Adventure,Comedy,Family,Music... United States,Taiwan,China Mandarin,Chinese,Min Nan,English During World War II in England, Charlie (Ian W... 78 movie 0 0 0 1 0 Disney+
4 15858 Tinker Bell and the Lost Treasure 2009 0 6.7 100 Klay Hall Mae Whitman,Jesse McCartney,Jane Horrocks,Lucy... Animation,Adventure,Family,Fantasy United States English A little girl comes to a town that is embattle... 81 movie 0 0 0 1 0 Disney+
In [38]:
fig = px.bar(y = disney_roto_high_movies['Title'][:15],
             x = disney_roto_high_movies['Rotten Tomatoes'][:15], 
             color = disney_roto_high_movies['Rotten Tomatoes'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Rotten Tomatoes : Rating'},
             title  = 'Movies with Highest Rotten Tomatoes : Disney+')

fig.update_layout(plot_bgcolor = 'white')
fig.show()
In [39]:
fig = px.bar(y = disney_roto_low_movies['Title'][:15],
             x = disney_roto_low_movies['Rotten Tomatoes'][:15], 
             color = disney_roto_low_movies['Rotten Tomatoes'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Rotten Tomatoes : Rating'},
             title  = 'Movies with Lowest Rotten Tomatoes : Disney+')

fig.update_layout(plot_bgcolor = 'white')
fig.show()
In [40]:
print(f'''
      The Movie with Highest Rotten Tomatoes  Ever Got is '{df_roto_high_movies['Title'][0]}' : '{df_roto_high_movies['Rotten Tomatoes'].max()}'\n
      The Movie with Lowest Rotten Tomatoes  Ever Got is '{df_roto_low_movies['Title'][0]}' : '{df_roto_low_movies['Rotten Tomatoes'].min()}'\n
      
      The Movie with Highest Rotten Tomatoes  on 'Netflix' is '{netflix_roto_high_movies['Title'][0]}' : '{netflix_roto_high_movies['Rotten Tomatoes'].max()}'\n
      The Movie with Lowest Rotten Tomatoes  on 'Netflix' is '{netflix_roto_low_movies['Title'][0]}' : '{netflix_roto_low_movies['Rotten Tomatoes'].min()}'\n
      
      The Movie with Highest Rotten Tomatoes  on 'Hulu' is '{hulu_roto_high_movies['Title'][0]}' : '{hulu_roto_high_movies['Rotten Tomatoes'].max()}'\n
      The Movie with Lowest Rotten Tomatoes  on 'Hulu' is '{hulu_roto_low_movies['Title'][0]}' : '{hulu_roto_low_movies['Rotten Tomatoes'].min()}'\n
      
      The Movie with Highest Rotten Tomatoes  on 'Prime Video' is '{prime_video_roto_high_movies['Title'][0]}' : '{prime_video_roto_high_movies['Rotten Tomatoes'].max()}'\n
      The Movie with Lowest Rotten Tomatoes  on 'Prime Video' is '{prime_video_roto_low_movies['Title'][0]}' : '{prime_video_roto_low_movies['Rotten Tomatoes'].min()}'\n
      
      The Movie with Highest Rotten Tomatoes  on 'Disney+' is '{disney_roto_high_movies['Title'][0]}' : '{disney_roto_high_movies['Rotten Tomatoes'].max()}'\n
      The Movie with Lowest Rotten Tomatoes  on 'Disney+' is '{disney_roto_low_movies['Title'][0]}' : '{disney_roto_low_movies['Rotten Tomatoes'].min()}'\n 
      ''')

      The Movie with Highest Rotten Tomatoes  Ever Got is 'Pyaasa' : '100'

      The Movie with Lowest Rotten Tomatoes  Ever Got is 'Term Life' : '0'

      
      The Movie with Highest Rotten Tomatoes  on 'Netflix' is 'Ice Guardians' : '100'

      The Movie with Lowest Rotten Tomatoes  on 'Netflix' is 'Term Life' : '0'

      
      The Movie with Highest Rotten Tomatoes  on 'Hulu' is 'After the Screaming Stops' : '100'

      The Movie with Lowest Rotten Tomatoes  on 'Hulu' is 'Four Lovers' : '0'

      
      The Movie with Highest Rotten Tomatoes  on 'Prime Video' is 'Pyaasa' : '100'

      The Movie with Lowest Rotten Tomatoes  on 'Prime Video' is 'Speed Kills' : '0'

      
      The Movie with Highest Rotten Tomatoes  on 'Disney+' is 'The Many Adventures of Winnie the Pooh' : '100'

      The Movie with Lowest Rotten Tomatoes  on 'Disney+' is 'Mulan II' : '0'
In [41]:
print(f'''
      Accross All Platforms the Average Rotten Tomatoes  is '{round(df_movies_roto['Rotten Tomatoes'].mean(), ndigits = 2)}'\n
      The Average Rotten Tomatoes  on 'Netflix' is '{round(netflix_roto_movies['Rotten Tomatoes'].mean(), ndigits = 2)}'\n
      The Average Rotten Tomatoes  on 'Hulu' is '{round(hulu_roto_movies['Rotten Tomatoes'].mean(), ndigits = 2)}'\n
      The Average Rotten Tomatoes  on 'Prime Video' is '{round(prime_video_roto_movies['Rotten Tomatoes'].mean(), ndigits = 2)}'\n
      The Average Rotten Tomatoes  on 'Disney+' is '{round(disney_roto_movies['Rotten Tomatoes'].mean(), ndigits = 2)}'\n 
      ''')

      Accross All Platforms the Average Rotten Tomatoes  is '63.95'

      The Average Rotten Tomatoes  on 'Netflix' is '64.64'

      The Average Rotten Tomatoes  on 'Hulu' is '65.85'

      The Average Rotten Tomatoes  on 'Prime Video' is '62.94'

      The Average Rotten Tomatoes  on 'Disney+' is '62.54'
In [42]:
f, ax = plt.subplots(1, 2 , figsize = (20, 5))
sns.distplot(df_movies_roto['Rotten Tomatoes'],bins = 20, kde = True, ax = ax[0])
sns.boxplot(df_movies_roto['Rotten Tomatoes'], ax = ax[1])
plt.show()
In [43]:
# Defining plot size and title
plt.figure(figsize = (20, 5))
plt.title('Rotten Tomatoes s Per Platform')
 
# Plotting the information from each dataset into a histogram
sns.histplot(prime_video_roto_movies['Rotten Tomatoes'][:100], color = 'lightblue', legend = True, kde = True)
sns.histplot(netflix_roto_movies['Rotten Tomatoes'][:100], color = 'red', legend = True, kde = True)
sns.histplot(hulu_roto_movies['Rotten Tomatoes'][:100], color = 'lightgreen', legend = True, kde = True)
sns.histplot(disney_roto_movies['Rotten Tomatoes'][:100], color = 'darkblue', legend = True, kde = True) 
 
# Setting the legend
plt.legend(['Prime Video', 'Netflix', 'Hulu', 'Disney+'])
plt.show()
In [44]:
def round_val(data):
    if str(data) != 'nan':
        return round(data)
        
def round_fix(data):
    if data in range(0,11):
        # print(data)
        return 10
    if data in range(11,21):
        return 20
    if data in range(21,31):
        return 30
    if data in range(31,41):
        return 40
    if data in range(41,51):
        return 50
    if data in range(51,61):
        return 60
    if data in range(61,71):
        return 70
    if data in range(71,81):
        return 80
    if data in range(81,91):
        return 90
    if data in range(91,101):
        return 100
In [45]:
df_movies_roto_group['Rotten Tomatoes Group'] = df_movies_roto['Rotten Tomatoes'].apply(round_fix)
 
roto_values = df_movies_roto_group['Rotten Tomatoes Group'].value_counts().sort_index(ascending = False).tolist()
roto_index = df_movies_roto_group['Rotten Tomatoes Group'].value_counts().sort_index(ascending = False).index
 
# roto_values, roto_index
In [46]:
roto_group_count = df_movies_roto_group.groupby('Rotten Tomatoes Group')['Title'].count()
roto_group_movies = df_movies_roto_group.groupby('Rotten Tomatoes Group')[['Netflix', 'Hulu', 'Prime Video', 'Disney+']].sum()
roto_group_data_movies = pd.concat([roto_group_count, roto_group_movies], axis = 1).reset_index().rename(columns = {'Title' : 'Movies Count'})
roto_group_data_movies = roto_group_data_movies.sort_values(by = 'Movies Count', ascending = False)
In [47]:
# Rotten Tomatoes Group with Movies Counts - All Platforms Combined
roto_group_data_movies.sort_values(by = 'Movies Count', ascending = False)
Out[47]:
Rotten Tomatoes Group Movies Count Netflix Hulu Prime Video Disney+
9 100 1265 386 128 746 61
8 90 1103 284 166 674 52
7 80 844 217 81 535 55
6 70 666 185 70 410 39
4 50 543 142 53 350 26
5 60 528 138 49 333 40
3 40 510 139 51 323 39
1 20 389 110 35 253 24
2 30 374 97 39 236 25
0 10 264 68 25 191 7
In [48]:
roto_group_data_movies.sort_values(by = 'Rotten Tomatoes Group', ascending = False)
Out[48]:
Rotten Tomatoes Group Movies Count Netflix Hulu Prime Video Disney+
9 100 1265 386 128 746 61
8 90 1103 284 166 674 52
7 80 844 217 81 535 55
6 70 666 185 70 410 39
5 60 528 138 49 333 40
4 50 543 142 53 350 26
3 40 510 139 51 323 39
2 30 374 97 39 236 25
1 20 389 110 35 253 24
0 10 264 68 25 191 7
In [49]:
fig = px.bar(y = roto_group_data_movies['Movies Count'],
             x = roto_group_data_movies['Rotten Tomatoes Group'], 
             color = roto_group_data_movies['Rotten Tomatoes Group'],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies Count', 'x' : 'Rotten Tomatoes : Rating'},
             title  = 'Movies with Group Rotten Tomatoes : All Platforms')

fig.update_layout(plot_bgcolor = "white")
fig.show()
In [50]:
fig = px.pie(roto_group_data_movies[:10],
             names = roto_group_data_movies['Rotten Tomatoes Group'],
             values = roto_group_data_movies['Movies Count'],
             color = roto_group_data_movies['Movies Count'],
             color_discrete_sequence = px.colors.sequential.Teal)

fig.update_traces(textinfo = 'percent+label',
                  title = 'Movies Count based on Rotten Tomatoes Group')
fig.show()
In [51]:
df_roto_group_high_movies = roto_group_data_movies.sort_values(by = 'Movies Count', ascending = False).reset_index()
df_roto_group_high_movies = df_roto_group_high_movies.drop(['index'], axis = 1)
# filter = (roto_group_data_movies['Movies Count'] ==  (roto_group_data_movies['Movies Count'].max()))
# df_roto_group_high_movies = roto_group_data_movies[filter]
 
# highest_rated_movies = roto_group_data_movies.loc[roto_group_data_movies['Movies Count'].idxmax()]
 
# print('\nRotten Tomatoes with Highest Ever Movies Count are : All Platforms Combined\n')
df_roto_group_high_movies.head(5)
Out[51]:
Rotten Tomatoes Group Movies Count Netflix Hulu Prime Video Disney+
0 100 1265 386 128 746 61
1 90 1103 284 166 674 52
2 80 844 217 81 535 55
3 70 666 185 70 410 39
4 50 543 142 53 350 26
In [52]:
df_roto_group_low_movies = roto_group_data_movies.sort_values(by = 'Movies Count', ascending = True).reset_index()
df_roto_group_low_movies = df_roto_group_low_movies.drop(['index'], axis = 1)
# filter = (roto_group_data_movies['Movies Count'] = =  (roto_group_data_movies['Movies Count'].min()))
# df_roto_group_low_movies = roto_group_data_movies[filter]
 
# print('\nRotten Tomatoes with Lowest Ever Movies Count are : All Platforms Combined\n')
df_roto_group_low_movies.head(5)
Out[52]:
Rotten Tomatoes Group Movies Count Netflix Hulu Prime Video Disney+
0 10 264 68 25 191 7
1 30 374 97 39 236 25
2 20 389 110 35 253 24
3 40 510 139 51 323 39
4 60 528 138 49 333 40
In [53]:
print(f'''
      Total '{df_movies_roto['Rotten Tomatoes'].count()}' Titles are available on All Platforms, out of which\n
      You Can Choose to see Movies from Total '{roto_group_data_movies['Rotten Tomatoes Group'].unique().shape[0]}' Rotten Tomatoes Group, They were Like this, \n
 
      {roto_group_data_movies.sort_values(by = 'Movies Count', ascending = False)['Rotten Tomatoes Group'].unique()} etc. \n
 
      The Rotten Tomatoes Group with Highest Movies Count have '{roto_group_data_movies['Movies Count'].max()}' Movies Available is '{df_roto_group_high_movies['Rotten Tomatoes Group'][0]}', &\n
      The Rotten Tomatoes Group with Lowest Movies Count have '{roto_group_data_movies['Movies Count'].min()}' Movies Available is '{df_roto_group_low_movies['Rotten Tomatoes Group'][0]}'
      ''')

      Total '6486' Titles are available on All Platforms, out of which

      You Can Choose to see Movies from Total '10' Rotten Tomatoes Group, They were Like this, 

 
      [100  90  80  70  50  60  40  20  30  10] etc. 

 
      The Rotten Tomatoes Group with Highest Movies Count have '1265' Movies Available is '100', &

      The Rotten Tomatoes Group with Lowest Movies Count have '264' Movies Available is '10'
In [54]:
netflix_roto_group_movies = roto_group_data_movies[roto_group_data_movies['Netflix'] !=  0].sort_values(by = 'Netflix', ascending = False).reset_index()
netflix_roto_group_movies = netflix_roto_group_movies.drop(['index', 'Hulu', 'Prime Video', 'Disney+', 'Movies Count'], axis = 1)
 
netflix_roto_group_high_movies = df_roto_group_high_movies.sort_values(by = 'Netflix', ascending = False).reset_index()
netflix_roto_group_high_movies = netflix_roto_group_high_movies.drop(['index'], axis = 1)
 
netflix_roto_group_low_movies = df_roto_group_high_movies.sort_values(by = 'Netflix', ascending = True).reset_index()
netflix_roto_group_low_movies = netflix_roto_group_low_movies.drop(['index'], axis = 1)
 
netflix_roto_group_high_movies.head(5)
Out[54]:
Rotten Tomatoes Group Movies Count Netflix Hulu Prime Video Disney+
0 100 1265 386 128 746 61
1 90 1103 284 166 674 52
2 80 844 217 81 535 55
3 70 666 185 70 410 39
4 50 543 142 53 350 26
In [55]:
hulu_roto_group_movies = roto_group_data_movies[roto_group_data_movies['Hulu'] !=  0].sort_values(by = 'Hulu', ascending = False).reset_index()
hulu_roto_group_movies = hulu_roto_group_movies.drop(['index', 'Netflix', 'Prime Video', 'Disney+', 'Movies Count'], axis = 1)
 
hulu_roto_group_high_movies = df_roto_group_high_movies.sort_values(by = 'Hulu', ascending = False).reset_index()
hulu_roto_group_high_movies = hulu_roto_group_high_movies.drop(['index'], axis = 1)
 
hulu_roto_group_low_movies = df_roto_group_high_movies.sort_values(by = 'Hulu', ascending = True).reset_index()
hulu_roto_group_low_movies = hulu_roto_group_low_movies.drop(['index'], axis = 1)
 
hulu_roto_group_high_movies.head(5)
Out[55]:
Rotten Tomatoes Group Movies Count Netflix Hulu Prime Video Disney+
0 90 1103 284 166 674 52
1 100 1265 386 128 746 61
2 80 844 217 81 535 55
3 70 666 185 70 410 39
4 50 543 142 53 350 26
In [56]:
prime_video_roto_group_movies = roto_group_data_movies[roto_group_data_movies['Prime Video'] !=  0].sort_values(by = 'Prime Video', ascending = False).reset_index()
prime_video_roto_group_movies = prime_video_roto_group_movies.drop(['index', 'Netflix', 'Hulu', 'Disney+', 'Movies Count'], axis = 1)
 
prime_video_roto_group_high_movies = df_roto_group_high_movies.sort_values(by = 'Prime Video', ascending = False).reset_index()
prime_video_roto_group_high_movies = prime_video_roto_group_high_movies.drop(['index'], axis = 1)
 
prime_video_roto_group_low_movies = df_roto_group_high_movies.sort_values(by = 'Prime Video', ascending = True).reset_index()
prime_video_roto_group_low_movies = prime_video_roto_group_low_movies.drop(['index'], axis = 1)
 
prime_video_roto_group_high_movies.head(5)
Out[56]:
Rotten Tomatoes Group Movies Count Netflix Hulu Prime Video Disney+
0 100 1265 386 128 746 61
1 90 1103 284 166 674 52
2 80 844 217 81 535 55
3 70 666 185 70 410 39
4 50 543 142 53 350 26
In [57]:
disney_roto_group_movies = roto_group_data_movies[roto_group_data_movies['Disney+'] !=  0].sort_values(by = 'Disney+', ascending = False).reset_index()
disney_roto_group_movies = disney_roto_group_movies.drop(['index', 'Netflix', 'Hulu', 'Prime Video', 'Movies Count'], axis = 1)
 
disney_roto_group_high_movies = df_roto_group_high_movies.sort_values(by = 'Disney+', ascending = False).reset_index()
disney_roto_group_high_movies = disney_roto_group_high_movies.drop(['index'], axis = 1)
 
disney_roto_group_low_movies = df_roto_group_high_movies.sort_values(by = 'Disney+', ascending = True).reset_index()
disney_roto_group_low_movies = disney_roto_group_low_movies.drop(['index'], axis = 1)
 
disney_roto_group_high_movies.head(5)
Out[57]:
Rotten Tomatoes Group Movies Count Netflix Hulu Prime Video Disney+
0 100 1265 386 128 746 61
1 80 844 217 81 535 55
2 90 1103 284 166 674 52
3 60 528 138 49 333 40
4 70 666 185 70 410 39
In [58]:
print(f'''
      The Rotten Tomatoes Group with Highest Movies Count Ever Got is '{df_roto_group_high_movies['Rotten Tomatoes Group'][0]}' : '{df_roto_group_high_movies['Movies Count'].max()}'\n
      The Rotten Tomatoes Group with Lowest Movies Count Ever Got is '{df_roto_group_low_movies['Rotten Tomatoes Group'][0]}' : '{df_roto_group_low_movies['Movies Count'].min()}'\n
      
      The Rotten Tomatoes Group with Highest Movies Count on 'Netflix' is '{netflix_roto_group_high_movies['Rotten Tomatoes Group'][0]}' : '{netflix_roto_group_high_movies['Netflix'].max()}'\n
      The Rotten Tomatoes Group with Lowest Movies Count on 'Netflix' is '{netflix_roto_group_low_movies['Rotten Tomatoes Group'][0]}' : '{netflix_roto_group_low_movies['Netflix'].min()}'\n
      
      The Rotten Tomatoes Group with Highest Movies Count on 'Hulu' is '{hulu_roto_group_high_movies['Rotten Tomatoes Group'][0]}' : '{hulu_roto_group_high_movies['Hulu'].max()}'\n
      The Rotten Tomatoes Group with Lowest Movies Count on 'Hulu' is '{hulu_roto_group_low_movies['Rotten Tomatoes Group'][0]}' : '{hulu_roto_group_low_movies['Hulu'].min()}'\n
      
      The Rotten Tomatoes Group with Highest Movies Count on 'Prime Video' is '{prime_video_roto_group_high_movies['Rotten Tomatoes Group'][0]}' : '{prime_video_roto_group_high_movies['Prime Video'].max()}'\n
      The Rotten Tomatoes Group with Lowest Movies Count on 'Prime Video' is '{prime_video_roto_group_low_movies['Rotten Tomatoes Group'][0]}' : '{prime_video_roto_group_low_movies['Prime Video'].min()}'\n
      
      The Rotten Tomatoes Group with Highest Movies Count on 'Disney+' is '{disney_roto_group_high_movies['Rotten Tomatoes Group'][0]}' : '{disney_roto_group_high_movies['Disney+'].max()}'\n
      The Rotten Tomatoes Group with Lowest Movies Count on 'Disney+' is '{disney_roto_group_low_movies['Rotten Tomatoes Group'][0]}' : '{disney_roto_group_low_movies['Disney+'].min()}'\n 
      ''')

      The Rotten Tomatoes Group with Highest Movies Count Ever Got is '100' : '1265'

      The Rotten Tomatoes Group with Lowest Movies Count Ever Got is '10' : '264'

      
      The Rotten Tomatoes Group with Highest Movies Count on 'Netflix' is '100' : '386'

      The Rotten Tomatoes Group with Lowest Movies Count on 'Netflix' is '10' : '68'

      
      The Rotten Tomatoes Group with Highest Movies Count on 'Hulu' is '90' : '166'

      The Rotten Tomatoes Group with Lowest Movies Count on 'Hulu' is '10' : '25'

      
      The Rotten Tomatoes Group with Highest Movies Count on 'Prime Video' is '100' : '746'

      The Rotten Tomatoes Group with Lowest Movies Count on 'Prime Video' is '10' : '191'

      
      The Rotten Tomatoes Group with Highest Movies Count on 'Disney+' is '100' : '61'

      The Rotten Tomatoes Group with Lowest Movies Count on 'Disney+' is '10' : '7'
In [59]:
fig, axes = plt.subplots(2, 2, figsize = (20 , 20))
 
n_ro_ax1 = sns.barplot(x = netflix_roto_group_movies['Rotten Tomatoes Group'][:10], y = netflix_roto_group_movies['Netflix'][:10], palette = 'Reds_r', ax = axes[0, 0])
h_ro_ax2 = sns.barplot(x = hulu_roto_group_movies['Rotten Tomatoes Group'][:10], y = hulu_roto_group_movies['Hulu'][:10], palette = 'Greens_r', ax = axes[0, 1])
p_ro_ax3 = sns.barplot(x = prime_video_roto_group_movies['Rotten Tomatoes Group'][:10], y = prime_video_roto_group_movies['Prime Video'][:10], palette = 'Blues_r', ax = axes[1, 0])
d_ro_ax4 = sns.barplot(x = disney_roto_group_movies['Rotten Tomatoes Group'][:10], y = disney_roto_group_movies['Disney+'][:10], palette = 'BuPu_r', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_ro_ax1.title.set_text(labels[0])
h_ro_ax2.title.set_text(labels[1])
p_ro_ax3.title.set_text(labels[2])
d_ro_ax4.title.set_text(labels[3])
 
plt.show()
In [60]:
plt.figure(figsize = (20, 5))
sns.lineplot(x = roto_group_data_movies['Rotten Tomatoes Group'], y = roto_group_data_movies['Netflix'], color = 'red')
sns.lineplot(x = roto_group_data_movies['Rotten Tomatoes Group'], y = roto_group_data_movies['Hulu'], color = 'lightgreen')
sns.lineplot(x = roto_group_data_movies['Rotten Tomatoes Group'], y = roto_group_data_movies['Prime Video'], color = 'lightblue')
sns.lineplot(x = roto_group_data_movies['Rotten Tomatoes Group'], y = roto_group_data_movies['Disney+'], color = 'darkblue')
plt.xlabel('Rotten Tomatoes Group', fontsize = 15)
plt.ylabel('Movies Count', fontsize = 15)
plt.show()
In [61]:
print(f'''
      Accross All Platforms Total Count of Rotten Tomatoes Group is '{roto_group_data_movies['Rotten Tomatoes Group'].unique().shape[0]}'\n
      Total Count of Rotten Tomatoes Group on 'Netflix' is '{netflix_roto_group_movies['Rotten Tomatoes Group'].unique().shape[0]}'\n
      Total Count of Rotten Tomatoes Group on 'Hulu' is '{hulu_roto_group_movies['Rotten Tomatoes Group'].unique().shape[0]}'\n
      Total Count of Rotten Tomatoes Group on 'Prime Video' is '{prime_video_roto_group_movies['Rotten Tomatoes Group'].unique().shape[0]}'\n
      Total Count of Rotten Tomatoes Group on 'Disney+' is '{disney_roto_group_movies['Rotten Tomatoes Group'].unique().shape[0]}'\n 
      ''')

      Accross All Platforms Total Count of Rotten Tomatoes Group is '10'

      Total Count of Rotten Tomatoes Group on 'Netflix' is '10'

      Total Count of Rotten Tomatoes Group on 'Hulu' is '10'

      Total Count of Rotten Tomatoes Group on 'Prime Video' is '10'

      Total Count of Rotten Tomatoes Group on 'Disney+' is '10'
In [62]:
fig, axes = plt.subplots(2, 2, figsize = (20 , 20))
 
n_ro_ax1 = sns.lineplot(y = roto_group_data_movies['Rotten Tomatoes Group'], x = roto_group_data_movies['Netflix'], color = 'red', ax = axes[0, 0])
h_ro_ax2 = sns.lineplot(y = roto_group_data_movies['Rotten Tomatoes Group'], x = roto_group_data_movies['Hulu'], color = 'lightgreen', ax = axes[0, 1])
p_ro_ax3 = sns.lineplot(y = roto_group_data_movies['Rotten Tomatoes Group'], x = roto_group_data_movies['Prime Video'], color = 'lightblue', ax = axes[1, 0])
d_ro_ax4 = sns.lineplot(y = roto_group_data_movies['Rotten Tomatoes Group'], x = roto_group_data_movies['Disney+'], color = 'darkblue', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_ro_ax1.title.set_text(labels[0])
h_ro_ax2.title.set_text(labels[1])
p_ro_ax3.title.set_text(labels[2])
d_ro_ax4.title.set_text(labels[3])

plt.show()
In [63]:
fig, axes = plt.subplots(2, 2, figsize = (20 , 20))
 
n_ro_ax1 = sns.barplot(x = roto_group_data_movies['Rotten Tomatoes Group'][:10], y = roto_group_data_movies['Netflix'][:10], palette = 'Reds_r', ax = axes[0, 0])
h_ro_ax2 = sns.barplot(x = roto_group_data_movies['Rotten Tomatoes Group'][:10], y = roto_group_data_movies['Hulu'][:10], palette = 'Greens_r', ax = axes[0, 1])
p_ro_ax3 = sns.barplot(x = roto_group_data_movies['Rotten Tomatoes Group'][:10], y = roto_group_data_movies['Prime Video'][:10], palette = 'Blues_r', ax = axes[1, 0])
d_ro_ax4 = sns.barplot(x = roto_group_data_movies['Rotten Tomatoes Group'][:10], y = roto_group_data_movies['Disney+'][:10], palette = 'BuPu_r', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_ro_ax1.title.set_text(labels[0])
h_ro_ax2.title.set_text(labels[1])
p_ro_ax3.title.set_text(labels[2])
d_ro_ax4.title.set_text(labels[3])
 
plt.show()